{"id":"https://openalex.org/W4407857407","doi":"https://doi.org/10.1145/3696443.3708951","title":"A Priori Loop Nest Normalization: Automatic Loop Scheduling in Complex Applications","display_name":"A Priori Loop Nest Normalization: Automatic Loop Scheduling in Complex Applications","publication_year":2025,"publication_date":"2025-02-22","ids":{"openalex":"https://openalex.org/W4407857407","doi":"https://doi.org/10.1145/3696443.3708951"},"language":"en","primary_location":{"id":"doi:10.1145/3696443.3708951","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696443.3708951","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3696443.3708951","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032133001","display_name":"Lukas Tr\u00fcmper","orcid":"https://orcid.org/0000-0002-0961-7723"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lukas Tr\u00fcmper","raw_affiliation_strings":["Daisytuner, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0961-7723","affiliations":[{"raw_affiliation_string":"Daisytuner, Darmstadt, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009037320","display_name":"Philipp Schaad","orcid":"https://orcid.org/0000-0002-8429-7803"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Philipp Schaad","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-8429-7803","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077055240","display_name":"Berke Ates","orcid":"https://orcid.org/0000-0003-0242-3640"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Berke Ates","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-0242-3640","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044806450","display_name":"Alexandru Calotoiu","orcid":"https://orcid.org/0000-0001-9095-9108"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alexandru Calotoiu","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-9095-9108","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077355144","display_name":"Marcin Copik","orcid":"https://orcid.org/0000-0002-7606-5519"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marcin Copik","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7606-5519","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-1333-9797","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5032133001"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02293059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"418","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10933","display_name":"Real-Time Systems Scheduling","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6820114254951477},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.6710479855537415},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6622606515884399},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6292543411254883},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.499164342880249},{"id":"https://openalex.org/keywords/loop-fission","display_name":"Loop fission","score":0.4498979151248932},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.36109960079193115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3118339776992798},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.15534359216690063},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14837142825126648}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6820114254951477},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.6710479855537415},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6622606515884399},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6292543411254883},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.499164342880249},{"id":"https://openalex.org/C134718785","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fission","level":3,"score":0.4498979151248932},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.36109960079193115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3118339776992798},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.15534359216690063},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14837142825126648},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3696443.3708951","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696443.3708951","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},{"id":"pmh:doi:10.3929/ethz-b-000729779","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.1145/3696443.3708951","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696443.3708951","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1191262899","https://openalex.org/W1558370006","https://openalex.org/W1964354616","https://openalex.org/W1997186449","https://openalex.org/W2000882268","https://openalex.org/W2128249697","https://openalex.org/W2172073571","https://openalex.org/W2245493112","https://openalex.org/W2613618711","https://openalex.org/W2949967139","https://openalex.org/W2955053021","https://openalex.org/W2961619211","https://openalex.org/W2987684178","https://openalex.org/W2997238241","https://openalex.org/W2999016616","https://openalex.org/W3002820667","https://openalex.org/W3004964720","https://openalex.org/W3035965352","https://openalex.org/W3090768939","https://openalex.org/W3099878876","https://openalex.org/W3099929288","https://openalex.org/W3146312719","https://openalex.org/W3151489216","https://openalex.org/W3160781636","https://openalex.org/W3175004880","https://openalex.org/W3184391514","https://openalex.org/W4281936325","https://openalex.org/W4282977501","https://openalex.org/W4321184926","https://openalex.org/W4381327222"],"related_works":["https://openalex.org/W1596526459","https://openalex.org/W2114948246","https://openalex.org/W154155438","https://openalex.org/W2058764256","https://openalex.org/W2016388920","https://openalex.org/W2481821631","https://openalex.org/W4205359103","https://openalex.org/W4256122319","https://openalex.org/W2017719803","https://openalex.org/W1988070942"],"abstract_inverted_index":{"The":[0],"same":[1,89,117],"computations":[2,16],"are":[3,19],"often":[4],"expressed":[5,20],"differently":[6],"across":[7],"software":[8],"projects":[9],"and":[10,29,65,75,102,173,179,191,196],"programming":[11],"languages.":[12],"In":[13,51],"particular,":[14],"how":[15],"involving":[17],"loops":[18],"varies":[21],"due":[22],"to":[23,27,42,61,87,99,112,203],"the":[24,67,70,88,93,116,126,133,137,174,201,204,214,223],"many":[25,47,109,140],"possibilities":[26],"permute":[28],"compose":[30],"loops.":[31],"Since":[32,92],"each":[33],"variant":[34],"may":[35],"have":[36],"unique":[37],"performance":[38,138],"properties,":[39],"automatic":[40],"approaches":[41],"loop":[43,58,63,80,100,110,142],"scheduling":[44],"must":[45],"support":[46],"different":[48,83,141,152],"optimization":[49,118],"recipes.":[50],"this":[52,106],"paper,":[53],"we":[54,73,124,154,199],"propose":[55],"a":[56,156,164,219],"priori":[57],"nest":[59,143],"normalization":[60,77,107,127],"align":[62],"nests":[64,81,111],"reduce":[66],"variation":[68],"before":[69],"optimization.":[71],"Specifically,":[72],"define":[74],"apply":[76,125,200],"criteria,":[78],"mapping":[79],"with":[82,128],"memory":[84,94],"access":[85,95],"patterns":[86],"canonical":[90,134],"form.":[91],"pattern":[96],"is":[97],"susceptible":[98],"variations":[101],"critical":[103],"for":[104,131],"performance,":[105],"allows":[108],"be":[113],"optimized":[114],"by":[115,163,177,193],"recipe.":[119],"To":[120],"evaluate":[121],"our":[122],"approach,":[123],"optimizations":[129],"designed":[130],"only":[132],"form,":[135],"improving":[136],"of":[139,148,166,213],"variants.":[144],"Across":[145],"multiple":[146],"implementations":[147],"15":[149],"benchmarks":[150],"using":[151],"languages,":[153],"outperform":[155],"baseline":[157],"compiler":[158],"in":[159],"C":[160],"on":[161],"average":[162],"factor":[165],"21.13,":[167],"state-of-the-art":[168],"auto-schedulers":[169],"such":[170,187],"as":[171,181,183,188],"Polly":[172],"Tiramisu":[175],"auto-scheduler":[176],"2.31":[178],"2.89,":[180],"well":[182],"performance-oriented":[184],"Python-based":[185],"frameworks":[186],"NumPy,":[189],"Numba,":[190],"DaCe":[192],"9.04,":[194],"3.92,":[195],"1.47.":[197],"Furthermore,":[198],"concept":[202],"CLOUDSC":[205],"cloud":[206],"microphysics":[207],"scheme,":[208],"an":[209],"actively":[210],"used":[211],"component":[212],"Integrated":[215],"Forecasting":[216],"System,":[217],"achieving":[218],"10%":[220],"speedup":[221],"over":[222],"highly-tuned":[224],"Fortran":[225],"code.":[226]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}